ClawHub
Back to skill

Security audit

AIML Voice Transcript

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it sends a user-selected audio file to AIMLAPI for transcription and returns or saves the transcript.

Install only if you are comfortable sending selected audio recordings to AIMLAPI for transcription. Avoid using it on confidential or sensitive recordings unless you understand AIMLAPI's data handling terms, and keep the API key limited to this service where possible.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tainted flow: 'req' from os.getenv (line 46, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
req = urllib.request.Request(url, data=data, headers=default_headers, method=method)
    try:
        with urllib.request.urlopen(req) as response:
            return json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as exc:
        detail = exc.read().decode("utf-8") if exc.fp else str(exc)
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill advertises executable behavior that uses environment variables, reads local audio files, writes transcript output, and sends data over the network, but it does not declare any explicit tool scope or permissions. This creates a transparency and policy-enforcement gap: an agent or operator may invoke the skill without clear consent boundaries, increasing the chance of unintended file access or external data transmission.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill says it will transcribe audio via AIMLAPI but does not clearly warn that user-provided audio files are uploaded to a third-party external service. This can cause users or calling agents to expose sensitive voice content, PII, or confidential recordings without informed consent, which is especially risky for voice messages that often contain personal data.

External Transmission

Medium
Category
Data Exfiltration
Content
import urllib.request
from typing import Any

DEFAULT_BASE_URL = "https://api.aimlapi.com/v1"
DEFAULT_USER_AGENT = "openclaw-skill-aimlapi-voice/1.1"

def parse_args() -> argparse.Namespace:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script uploads the full local audio file to a third-party transcription service, but only emits an informational message in verbose mode. In agent or automated contexts, this can cause unintentional disclosure of sensitive voice content or background audio to an external provider without clear user awareness or consent.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The code accesses sensitive authentication material via AIMLAPI_API_KEY or a user-supplied key file. There is no user-facing message, prompt, or inline explanatory comment near the access, so the credential handling is not clearly disclosed within the code.

Static analysis

No suspicious patterns detected.